Related papers: Context Forcing: Consistent Autoregressive Video G…

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient…

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training…

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Despite the significant progress that has been made in video generative models, existing state-of-the-art methods can only produce videos lasting 5-16 seconds, often labeled "long-form videos". Furthermore, videos exceeding 16 seconds…

Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional…

Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extending these models to generate long, cross-scene videos…

Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under practical computation and memory constraints, many…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Video generation has witnessed great success recently, but their application in generating long videos still remains challenging due to the difficulty in maintaining the temporal consistency of generated videos and the high memory cost…

Long-context modelling for large language models (LLMs) has been a key area of recent research because many real world use cases require reasoning over longer inputs such as documents. The focus of research into modelling long context has…

Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse datasets for long-context instruction tuning. Existing data…

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…

Bridging vision and natural language is a longstanding goal in computer vision and multimedia research. While earlier works focus on generating a single-sentence description for visual content, recent works have studied paragraph…

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…

We introduce a bootstrapping approach to train long-context language models by exploiting their short-context capabilities only. Our method utilizes a simple agent workflow to synthesize diverse long-context instruction tuning data, thereby…

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…